© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18539
    Prev
    Next
    INDEX
    Explanations

    verbs indicating change or development

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "have" indicating possession or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Quote
    -0.62
    inance
    -0.61
    soever
    -0.60
    dding
    -0.59
     shalt
    -0.59
     prosecuting
    -0.58
     quote
    -0.56
     Useful
    -0.55
     consult
    -0.55
    amine
    -0.55
    POSITIVE LOGITS
     deteriorated
    1.40
     disappeared
    1.34
     vanished
    1.30
     fallen
    1.29
     undergone
    1.25
     been
    1.25
     begun
    1.17
     shrunk
    1.17
     shifted
    1.16
     dwind
    1.16
    Activations Density 0.180%

    No Known Activations